CheenDing · CheenDing · May 24, 2026
diff --git a/packages/markitdown/src/markitdown/converters/_pptx_converter.py b/packages/markitdown/src/markitdown/converters/_pptx_converter.py
@@ -161,10 +161,11 @@ def get_shape_content(shape, **kwargs):
 
                 # Text areas
                 elif shape.has_text_frame:
+                    text = self._convert_text_frame_to_markdown(shape.text_frame)
                     if shape == title:
-                        md_content += "# " + shape.text.lstrip() + "\n"
+                        md_content += "# " + text.lstrip() + "\n"
                     else:
-                        md_content += shape.text + "\n"
+                        md_content += text + "\n"
 
                 # Group Shapes
                 if shape.shape_type == pptx.enum.shapes.MSO_SHAPE_TYPE.GROUP:
@@ -212,6 +213,35 @@ def _is_table(self, shape):
             return True
         return False
 
+    def _convert_text_frame_to_markdown(self, text_frame):
+        """Convert a text frame to markdown, preserving hyperlinks and list hierarchy."""
+        paragraphs_md = []
+        for para in text_frame.paragraphs:
+            para_md = self._convert_paragraph_to_markdown(para)
+            if para_md.strip():
+                paragraphs_md.append(para_md)
+        return "\n".join(paragraphs_md)
+
+    def _convert_paragraph_to_markdown(self, paragraph):
+        """Convert a single paragraph to markdown, preserving hyperlinks."""
+        runs_md = []
+        for run in paragraph.runs:
+            run_text = run.text
+            if run.hyperlink.address:
+                # Escape brackets in link text to avoid breaking markdown syntax
+                escaped_text = run_text.replace("[", "\\[").replace("]", "\\]")
+                run_text = f"[{escaped_text}]({run.hyperlink.address})"
+            runs_md.append(run_text)
+
+        text = "".join(runs_md)
+
+        # Handle list indentation based on paragraph level
+        if paragraph.level > 0 and text.strip():
+            indent = "  " * paragraph.level
+            text = indent + "- " + text
+
+        return text
+
     def _convert_table_to_markdown(self, table, **kwargs):
         # Write the table as HTML, then convert it to Markdown
         html_table = "<html><body><table>"

diff --git a/packages/markitdown/tests/_test_vectors.py b/packages/markitdown/tests/_test_vectors.py
@@ -234,6 +234,21 @@ class FileTestVector(object):
         ],
         must_not_include=[],
     ),
+    FileTestVector(
+        filename="test_hyperlinks.pptx",
+        mimetype="application/vnd.openxmlformats-officedocument.presentationml.presentation",
+        charset=None,
+        url=None,
+        must_include=[
+            "[Visit Microsoft](https://microsoft.com)",
+            "  - Second level item",
+            "    - Third level item",
+            "  - [GitHub link in list](https://github.com)",
+        ],
+        must_not_include=[
+            "Visit Microsofthttps://microsoft.com",  # ensure hyperlink is formatted, not plain text concatenation
+        ],
+    ),
 ]
 
 

diff --git a/packages/markitdown/tests/test_files/test_hyperlinks.pptx b/packages/markitdown/tests/test_files/test_hyperlinks.pptx